  
|
e9366d7f79
|
Updated b200 kimi-k3 cookbook (#33038)
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
|
2026-08-02 23:16:39 -07:00 |
|
nvjullin
|
b41552334d
|
Fix disagg speculative decoding with NIXL connector (#30222)
|
2026-07-06 15:51:33 -07:00 |
|
nvjullin
|
2f730e299f
|
Disable dsr1 prefill cudagraphs by default (#28053)
|
2026-06-30 16:34:44 +08:00 |
|
nvjullin
|
84a7a84018
|
[PD] Fix data race in NixlKVManager for NIXL backend (#28897)
|
2026-06-24 18:11:01 +08:00 |
|
nvjullin
|
cadfa2d025
|
Support piecewise CUDA graph with NSA (#23351)
|
2026-05-22 14:39:50 -07:00 |
|
nvjullin
|
3fe93b5493
|
Updated benchmark guide (#19243)
|
2026-02-24 21:11:17 -08:00 |
|
nvjullin
|
9a71500cfb
|
Fixed aarch64 flash-mla (#12009)
|
2025-10-23 17:47:04 -07:00 |
|